Commit graph

17 commits

Author SHA1 Message Date
Rhys Perry
6f368431fd aco/gfx11: workaround VALUMaskWriteHazard
fossil-db (gfx1100):
Totals from 62812 (46.52% of 135032) affected shaders:
Instrs: 43971580 -> 44069887 (+0.22%)
CodeSize: 233473420 -> 233866648 (+0.17%)
Latency: 463487489 -> 463520688 (+0.01%); split: -0.00%, +0.01%
InvThroughput: 86505748 -> 86509679 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18273>
2022-10-19 02:46:03 +00:00
Rhys Perry
5806f0246f aco/gfx11: workaround VALUPartialForwardingHazard
fossil-db (gfx1100):
Totals from 18121 (13.42% of 135032) affected shaders:
Instrs: 28272367 -> 28323468 (+0.18%)
CodeSize: 152581916 -> 152786320 (+0.13%)
Latency: 366477785 -> 366482318 (+0.00%); split: -0.00%, +0.00%
InvThroughput: 74475188 -> 74475758 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18273>
2022-10-19 02:46:03 +00:00
Rhys Perry
b0b48b7687 aco/gfx11: workaround VALUTransUseHazard
fossil-db (gfx1100):
Totals from 116990 (86.64% of 135032) affected shaders:
Instrs: 67942325 -> 69493991 (+2.28%)
CodeSize: 366448984 -> 372655648 (+1.69%)
Latency: 673236871 -> 673269808 (+0.00%); split: -0.00%, +0.00%
InvThroughput: 128266905 -> 128270175 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18273>
2022-10-19 02:46:03 +00:00
Rhys Perry
98ee3e1468 aco/gfx11: workaround LdsDirectVMEMHazard
fossil-db (gfx1100):
Totals from 27217 (20.16% of 135032) affected shaders:
Instrs: 18010853 -> 18047277 (+0.20%)
CodeSize: 99369568 -> 99515264 (+0.15%)
Latency: 207454040 -> 207464932 (+0.01%); split: -0.00%, +0.01%
InvThroughput: 39810158 -> 39810628 (+0.00%); split: -0.00%, +0.00%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18273>
2022-10-19 02:46:03 +00:00
Rhys Perry
296b4d95a3 aco/gfx11: workaround LdsDirectVALUHazard
fossil-db (gfx1100):
Totals from 57858 (42.85% of 135032) affected shaders:

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18273>
2022-10-19 02:46:03 +00:00
Rhys Perry
1a9840b341 aco/gfx11: workaround VcmpxPermlaneHazard
Same as GFX10, but in a separate pass because it's the only hazard that's
shared.

No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18273>
2022-10-19 02:46:03 +00:00
Rhys Perry
2bd16256a6 aco: fix VMEMtoScalarWriteHazard s_waitcnt mitigation
It doesn't make sense for a "s_waitcnt vmcnt(0)" to affect a store or DS
instruction.

LLVM checks for "s_waitcnt vmcnt(0) lgkmcnt(0) expcnt(0)" but ignores
s_waitcnt_vscnt (which I assume is a bug).

No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: bcf94bb933 ("aco: properly recognize that s_waitcnt mitigates VMEMtoScalarWriteHazard")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18270>
2022-09-30 11:44:38 +00:00
Rhys Perry
bf0af80045 aco: improve VcmpxPermlaneHazard workaround
According to LLVM, we only need to care about VOPC which writes exec.

No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17697>
2022-08-08 13:59:17 +00:00
Georg Lehmann
5dab077824 aco: Add a note about G16 without A16 to README-ISA.md.
Signed-off-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16979>
2022-07-26 16:54:08 +00:00
Timur Kristóf
5c35040da1 aco: Don't write m0 register for LDS instructions on GFX9+.
Fossil DB stats on Sienna Cichlid:

Totals from 2691 (2.09% of 128647) affected shaders:
VGPRs: 124392 -> 124376 (-0.01%)
CodeSize: 8192352 -> 8174620 (-0.22%); split: -0.22%, +0.00%
MaxWaves: 61516 -> 61524 (+0.01%)
Instrs: 1519774 -> 1514958 (-0.32%); split: -0.32%, +0.00%
Latency: 14767555 -> 14766145 (-0.01%); split: -0.01%, +0.00%
InvThroughput: 3394282 -> 3394173 (-0.00%); split: -0.01%, +0.00%
VClause: 31985 -> 32002 (+0.05%); split: -0.02%, +0.07%
SClause: 47581 -> 47539 (-0.09%); split: -0.14%, +0.05%
Copies: 127533 -> 122709 (-3.78%); split: -3.80%, +0.02%
Branches: 39395 -> 39390 (-0.01%)
PreSGPRs: 84389 -> 82702 (-2.00%)
PreVGPRs: 87520 -> 87519 (-0.00%)

Fossil DB stats on Sienna Cichlid with NGGC on:

Totals from 60930 (47.36% of 128647) affected shaders:
VGPRs: 2180712 -> 2180696 (-0.00%)
CodeSize: 169122736 -> 167474304 (-0.97%); split: -0.97%, +0.00%
MaxWaves: 1703698 -> 1703706 (+0.00%)
Instrs: 32301234 -> 31888743 (-1.28%); split: -1.28%, +0.00%
Latency: 152526083 -> 152367301 (-0.10%); split: -0.10%, +0.00%
InvThroughput: 25090218 -> 25089812 (-0.00%); split: -0.00%, +0.00%
VClause: 577302 -> 577319 (+0.00%); split: -0.00%, +0.00%
SClause: 801614 -> 801572 (-0.01%); split: -0.01%, +0.00%
Copies: 3399700 -> 2987201 (-12.13%); split: -12.13%, +0.00%
Branches: 1262859 -> 1262854 (-0.00%)
PreSGPRs: 2175752 -> 2141331 (-1.58%)
PreVGPRs: 1785088 -> 1785087 (-0.00%)

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11224>
2021-09-29 16:00:19 +02:00
Timur Kristóf
228169c87c aco: Add note about v_alignbyte in the ISA README.
We tried to use this instruction for a more optimal sequence,
but it turned out that it doesn't exactly work as it was
supposed to. This note is to help others who want to use it.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11072>
2021-06-09 16:48:51 +00:00
Samuel Pitoiset
3761d994f6 aco: fix range checking for SSBO loads/stores with SGPR offset on GFX6-7
GFX6-7 are affected by a hw bug that prevents address clamping to work
correctly when the SGPR offset is used. Use the VGPR offset to fix it.

Fixes various hangs with dEQP-VK.robustness.robustness2.* on Bonaire.

Cc: 21.1 mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11238>
2021-06-09 06:40:16 +00:00
Rhys Perry
903f814b78 aco: don't create 4 and 5 dword NSA instructions on GFX10
"stability issues", apparently: https://reviews.llvm.org/D103348

fossil-db (Navi10):
Totals from 4512 (3.01% of 149839) affected shaders:
VGPRs: 221516 -> 223308 (+0.81%); split: -0.07%, +0.88%
CodeSize: 23000080 -> 23070672 (+0.31%); split: -0.08%, +0.39%
MaxWaves: 107718 -> 107496 (-0.21%); split: +0.11%, -0.32%
Instrs: 4321890 -> 4362822 (+0.95%); split: -0.00%, +0.95%
Latency: 71495710 -> 71581476 (+0.12%); split: -0.07%, +0.19%
InvThroughput: 11858568 -> 11938960 (+0.68%); split: -0.00%, +0.68%
VClause: 76575 -> 76585 (+0.01%); split: -0.05%, +0.07%
SClause: 168771 -> 168709 (-0.04%); split: -0.06%, +0.02%
Copies: 182305 -> 221948 (+21.75%); split: -0.00%, +21.75%
PreVGPRs: 194657 -> 195635 (+0.50%); split: -0.00%, +0.50%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Fixes: c353895c92 ("aco: use non-sequential addressing")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10898>
2021-06-03 03:49:07 +00:00
Rhys Perry
81162265b1 aco: do not clause NSA instructions
According to LLVM, this has "unpredictable results on GFX10.1".

https://reviews.llvm.org/D102211

fossil-db (Navi10):
Totals from 26690 (17.81% of 149839) affected shaders:
CodeSize: 167935160 -> 167706280 (-0.14%); split: -0.14%, +0.00%
Instrs: 31801427 -> 31744142 (-0.18%); split: -0.18%, +0.00%
Latency: 732672435 -> 732622463 (-0.01%)
InvThroughput: 163361435 -> 163357838 (-0.00%); split: -0.00%, +0.00%
VClause: 546131 -> 546903 (+0.14%); split: -0.00%, +0.14%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Fixes: c353895c92 ("aco: use non-sequential addressing")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10898>
2021-06-03 03:49:07 +00:00
Timur Kristóf
38da379b3e aco: Note if rasterization can start early.
When there are no param exports in an NGG (or legacy VS) shader,
the NO_PC_EXPORT=1 is set by RADV, which means PS waves can launch
before the current stage finishes.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7868>
2021-01-12 16:43:27 +00:00
Timur Kristóf
b4d4c548eb aco: Fixup markdown formatting of the README-ISA.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4164>
2020-09-01 10:41:34 +00:00
Timur Kristóf
086fafc4e0 aco: Move README to README-ISA
The old "readme" is not really a readme but rather just
a bunch of notes with our findings about the GCN/RDNA ISA.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4164>
2020-09-01 10:41:34 +00:00
Renamed from src/amd/compiler/README.md (Browse further)